CN112233795A - Disease prediction system based on ear texture features - Google Patents
Disease prediction system based on ear texture features Download PDFInfo
- Publication number
- CN112233795A CN112233795A CN202011300974.3A CN202011300974A CN112233795A CN 112233795 A CN112233795 A CN 112233795A CN 202011300974 A CN202011300974 A CN 202011300974A CN 112233795 A CN112233795 A CN 112233795A
- Authority
- CN
- China
- Prior art keywords
- ear
- texture
- similarity
- lbp
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 53
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 53
- 238000005070 sampling Methods 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000010276 construction Methods 0.000 claims abstract description 11
- 238000005259 measurement Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 7
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 238000012216 screening Methods 0.000 abstract description 3
- 230000001149 cognitive effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 239000000243 solution Substances 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 210000000624 ear auricle Anatomy 0.000 description 7
- 210000005069 ears Anatomy 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 208000024891 symptom Diseases 0.000 description 5
- 230000001154 acute effect Effects 0.000 description 4
- 208000029078 coronary artery disease Diseases 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 206010008479 Chest Pain Diseases 0.000 description 2
- 206010033557 Palpitations Diseases 0.000 description 2
- 206010044302 Tracheitis Diseases 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 208000019622 heart disease Diseases 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 206010003011 Appendicitis Diseases 0.000 description 1
- 206010005963 Bone formation increased Diseases 0.000 description 1
- 206010008111 Cerebral haemorrhage Diseases 0.000 description 1
- 201000006306 Cor pulmonale Diseases 0.000 description 1
- 206010013789 Dry throat Diseases 0.000 description 1
- 206010016654 Fibrosis Diseases 0.000 description 1
- 206010018367 Glomerulonephritis chronic Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 206010068319 Oropharyngeal pain Diseases 0.000 description 1
- 208000002193 Pain Diseases 0.000 description 1
- 206010033733 Papule Diseases 0.000 description 1
- 201000007100 Pharyngitis Diseases 0.000 description 1
- 208000004186 Pulmonary Heart Disease Diseases 0.000 description 1
- 206010000496 acne Diseases 0.000 description 1
- 208000012876 acute enteritis Diseases 0.000 description 1
- 230000003143 atherosclerotic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000019658 bitter taste Nutrition 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000005282 brightening Methods 0.000 description 1
- 201000009267 bronchiectasis Diseases 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 238000002192 cholecystectomy Methods 0.000 description 1
- 201000001352 cholecystitis Diseases 0.000 description 1
- 201000001883 cholelithiasis Diseases 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 208000021735 chronic enteritis Diseases 0.000 description 1
- 230000007882 cirrhosis Effects 0.000 description 1
- 208000019425 cirrhosis of liver Diseases 0.000 description 1
- 201000003146 cystitis Diseases 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 239000003221 ear drop Substances 0.000 description 1
- 229940047652 ear drops Drugs 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000232 gallbladder Anatomy 0.000 description 1
- 208000001130 gallstones Diseases 0.000 description 1
- 208000007565 gingivitis Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000017169 kidney disease Diseases 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 208000019423 liver disease Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 201000008383 nephritis Diseases 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 201000001245 periodontitis Diseases 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 208000008128 pulmonary tuberculosis Diseases 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Abstract
The invention provides a disease prediction system based on ear texture characteristics. The method comprises the following steps: the characteristic extraction module is used for acquiring an ear texture picture and extracting an ear standard LBP texture characteristic vector from the ear texture picture; the construction module is used for establishing a feature identification model according to the ear standard LBP texture feature vector; the processing module is used for acquiring a to-be-identified ear sampling image, processing the to-be-identified ear sampling image and acquiring an LBP texture feature vector of the to-be-identified ear; and the prediction module is used for setting a similarity threshold, calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, comparing the similarity with the similarity threshold, and predicting the sampled image of the ear to be recognized according to the comparison result. According to the invention, the abnormal representation of the ear image acquired by the computer is processed, and then the semantic cognitive characteristic calculation is carried out, so that the functional state of the human body can be accurately and objectively reflected, and the accuracy of classification and identification of the local image sampling characteristic and the disease screening efficiency are improved.
Description
Technical Field
The invention relates to the field of computers, in particular to a disease prediction system based on ear texture features.
Background
The ears are the miniature of the organs and tissues of the human body, and the visceral organs, parts and ears of the human body have concentrated reflection points, so that the pathological changes of the organs and tissues are reflected in the ears inevitably. Ear diagnosis is to predict health and diagnose diseases by observing changes in position, size, shape, color, blood vessels, etc. of ears.
At present, the existing ear diagnosis mode is to predict diseases through some basic conventional features extracted by a basic image processing method by manually positioning an interested region in medical image feature extraction, but the accuracy of the mode is not high enough, and the mode is relatively dependent on the selection of a worker on the region, which is easy to cause omission, so that further improvement on the existing technology is urgently needed.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
In view of the above, the present invention provides a disease prediction system based on ear texture features, and aims to solve the technical problem that the prior art cannot improve the accurate extraction of ear feature images by using a similarity measurement function and a semantic cognition identification method.
The technical scheme of the invention is realized as follows:
in one aspect, the present invention provides an ear texture feature-based disease prediction system, including:
the characteristic extraction module is used for acquiring an ear texture picture and extracting an ear standard LBP texture characteristic vector from the ear texture picture;
the construction module is used for establishing a feature identification model according to the ear standard LBP texture feature vector;
the processing module is used for acquiring a sampling image of an ear to be identified, processing the sampling image of the ear to be identified and acquiring an LBP texture feature vector of the ear to be identified;
and the prediction module is used for setting a similarity threshold, calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, comparing the similarity with the similarity threshold, and predicting the sampled image of the ear to be recognized according to the comparison result.
On the basis of the above technical solution, preferably, the feature extraction module includes an LBP value obtaining module, configured to obtain an ear texture picture, divide the ear texture picture into small regions of 16X16, obtain a gray value of each pixel in each small region, compare the gray value of each pixel with gray values of 8 pixels adjacent to the pixel, and mark the pixel with a position of 1 when the gray value of each pixel is greater than the gray values of 8 pixels adjacent to the pixel; when the gray value of each pixel is less than the gray values of 8 pixels adjacent to the pixel, marking the position of the pixel as 0, and counting the position values of all the pixels as the LBP value of the area.
On the basis of the above technical solution, preferably, the feature extraction module includes an LBP texture feature vector extraction module, configured to set a spatial arrangement order, arrange each small region in a row according to the spatial arrangement order, and obtain an ear standard LBP texture feature vector of the ear texture picture according to an LBP value of each small region.
On the basis of the above technical solution, preferably, the building module includes a model building module, configured to obtain corresponding disease information according to the ear standard LBP texture feature vector, and build a feature identification model according to a mapping relationship between the ear standard LBP texture feature vector and the disease information.
On the basis of the above technical solution, preferably, the processing module includes a preprocessing module, configured to obtain a sampled image of an ear to be identified, perform integrity verification on the sampled image of the ear to be identified, and extract an LBP texture feature vector of the ear to be identified from the sampled image of the ear to be identified that passes the integrity verification.
On the basis of the above technical solution, preferably, the prediction module includes a calculation module, configured to establish an NCC principle similarity measurement function, and calculate, through the NCC principle similarity measurement function, a similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized.
On the basis of the above technical solution, preferably, the prediction module includes a matching prediction module, configured to set a similarity threshold, compare the similarity with the similarity threshold, and predict, through the feature recognition model, the ear to be recognized sample image corresponding to the LBP texture feature vector of the ear to be recognized when the similarity is greater than the similarity threshold; and when the similarity is smaller than the similarity threshold value, reselecting the similarity for comparison.
Still further preferably, the ear texture feature-based disease prediction apparatus includes:
the characteristic extraction unit is used for acquiring an ear texture picture and extracting an ear standard LBP texture characteristic vector from the ear texture picture;
the construction unit is used for establishing a feature identification model according to the ear standard LBP texture feature vector;
the processing unit is used for acquiring a sampling image of the ear to be identified, processing the sampling image of the ear to be identified and acquiring an LBP texture feature vector of the ear to be identified;
and the prediction unit is used for setting a similarity threshold, calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, comparing the similarity with the similarity threshold, and predicting the sampled image of the ear to be recognized according to the comparison result.
Compared with the prior art, the disease prediction system based on the ear texture features has the following beneficial effects:
(1) by extracting the characteristics of the ear images collected by the computer, the functional state of the human body can be accurately and objectively reflected, and the accuracy of classification and identification of the sampling characteristics of the local images and the disease screening efficiency are improved;
(2) by utilizing the NCC principle similarity measurement function, the accuracy and efficiency between data calculations can be improved, and meanwhile, the accuracy of disease prediction can be synchronously improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a first embodiment of the ear texture based disease prediction system of the present invention;
FIG. 2 is a block diagram of a disease prediction system based on ear texture features according to a second embodiment of the present invention;
FIG. 3 is a block diagram of a disease prediction system based on ear texture features according to a third embodiment of the present invention;
FIG. 4 is a block diagram illustrating a fourth embodiment of the ear texture based disease prediction system according to the present invention;
FIG. 5 is a block diagram of a fifth embodiment of the ear texture based disease prediction system according to the present invention;
fig. 6 is a block diagram of the disease prediction device based on ear texture features according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Fig. 1 is a block diagram illustrating a first embodiment of a disease prediction system based on ear texture features according to the present invention. Wherein the ear texture feature-based disease prediction system comprises: feature extraction module 10, construction module 20, processing module 30 and prediction module 40.
The feature extraction module 10 is configured to obtain an ear texture picture, and extract an ear standard LBP texture feature vector from the ear texture picture;
a building module 20, configured to build a feature identification model according to the ear standard LBP texture feature vector;
the processing module 30 is configured to obtain a sampling image of an ear to be identified, process the sampling image of the ear to be identified, and obtain an LBP texture feature vector of the ear to be identified;
and the prediction module 40 is configured to set a similarity threshold, calculate a similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, compare the similarity with the similarity threshold, and predict the sampled image of the ear to be recognized according to a comparison result.
Further, as shown in fig. 2, a block diagram of a second embodiment of the disease prediction system based on ear texture features is proposed based on the above embodiments, in this embodiment, the feature extraction module 10 further includes:
an LBP value obtaining module 101, configured to obtain an ear texture picture, divide the ear texture picture into small regions of 16X16, obtain a gray level value of each pixel in each small region, compare the gray level value of each pixel with the gray level values of 8 pixels adjacent to the pixel, and mark the pixel with a position of 1 when the gray level value of each pixel is greater than the gray level values of 8 pixels adjacent to the pixel; when the gray value of each pixel is less than the gray values of 8 pixels adjacent to the pixel, marking the position of the pixel as 0, and counting the position values of all the pixels as the LBP value of the area.
The LBP texture feature vector extraction module 102 is configured to set a spatial arrangement order, arrange each small region in a row according to the spatial arrangement order, and obtain an ear standard LBP texture feature vector of the ear texture picture according to an LBP value of each small region.
It should be understood that, in the embodiment of the present invention, an ear texture picture is obtained first, and then an LBP texture feature vector is extracted from the ear texture picture, which includes the following specific operation steps: firstly, dividing a normal ear detection window into 16X16 small regions, then obtaining an ear texture picture, then placing the ear texture picture into the ear detection window, namely dividing the ear texture picture into 16X16 small regions, then comparing the gray values of 8 adjacent pixels with one pixel in each region, if the peripheral pixel value is greater than the central pixel value, marking the position of the pixel as 1, otherwise, marking the position as 0. Thus, 8 points in the 3-by-3 neighborhood can generate 8-bit binary numbers through comparison, namely the LBP value of the pixel point in the center of the window is obtained, and then the system calculates the histogram of each area, namely the frequency of occurrence of each number (assumed as a decimal LBP value); then, the histogram is normalized, and finally, the obtained statistical histograms of all the regions are connected to form a feature vector, namely a standard LBP texture feature vector of the whole graph. For example: a picture with the size of 100 × 100 pixels of an ear can be divided into 10 × 100 sub-regions (the regions can be divided in various ways), and the size of each sub-region is 10 × 10 pixels; extracting LBP characteristics of each pixel point in each sub-region, and then establishing a statistical histogram; thus, there are 10 × 10 sub-regions in the picture, and there are 10 × 10 statistical histograms, and the picture can be described by using the 10 × 10 statistical histograms.
Further, as shown in fig. 3, a block diagram of a third embodiment of the disease prediction system based on ear texture features is proposed based on the above embodiments, in this embodiment, the building module 20 further includes:
the model establishing module 201 is configured to obtain corresponding disease information according to the ear standard LBP texture feature vector, and establish a feature identification model according to a mapping relationship between the ear standard LBP texture feature vector and the disease information.
It should be understood that after obtaining the ear standard LBP texture feature vector, the system will obtain corresponding disease information according to the ear standard LBP texture feature vector for the subsequent steps, where the disease information includes: the disease semantic description information and the corresponding solution establish an ear sampling image feature NCC similarity measurement function and a semantic cognition feature recognition model according to the LBP texture abnormal feature vector of the ear local image and the mapping relation between semantic description and the disease. For example, 1, the corresponding parts of the auricle have a nodular bulge or a dotted depression, a circular depression, a cord-like bulge and criss-cross lines, which are commonly seen in liver diseases, cholelithiasis, pulmonary tuberculosis, heart diseases, tumors, etc. For example, in patients with cirrhosis, there are many bumps and nodules in the auricle liver region, and the edges are clear; 2. punctate bulges higher than the surrounding skin appear on the corresponding parts of auricles, and the bulges are vesicular papules which are commonly called as egg pimples, red or white in color and commonly seen in diseases such as acute and chronic tracheitis, acute and chronic enteritis, acute and chronic appendicitis, acute and chronic nephritis, cystitis and the like; 3. the ear pendants have rough and uneven spinous process-like structures, and are commonly seen in diseases such as lumbar and cervical hyperosteogeny; 4. the earlobe has a stria obliterans with obvious wrinkles from the front to the back and down (which can occur in one ear or in both ears), which is common in patients with coronary atherosclerotic heart disease (coronary heart disease); 5. the earface skin vessels are easy to fill and are commonly seen in diseases such as bronchiectasis, coronary heart disease, myocardial infarction, hypertension and the like; 6. the ear drops are thin and brown, and are commonly seen in kidney diseases and diabetes; 7. a thick auricle means that the body is also obese and tends to cause cerebral hemorrhage.
Further, as shown in fig. 4, a block diagram of a fourth embodiment of the disease prediction system based on ear texture features is proposed based on the above embodiments, in this embodiment, the processing module 30 includes:
the preprocessing module 301 is configured to obtain a sampling image of an ear to be identified, perform integrity verification on the sampling image of the ear to be identified, and extract an LBP texture feature vector of the ear to be identified from the sampling image of the ear to be identified that passes the integrity verification.
It should be understood that, in order to facilitate subsequent calculation of the system, after the system acquires the sampled image of the ear to be recognized, the system performs integrity verification on the acquired sampled image of the ear to be recognized, where this integrity verification is a well-known method for detecting the integrity of a picture, and this embodiment is not described in detail, and then extracts the LBP texture feature vector of the ear to be recognized from the sampled image of the ear to be recognized that passes the integrity verification, that is, the extraction method described in the above embodiment.
Further, as shown in fig. 5, a block diagram of a fifth embodiment of the disease prediction system based on ear texture features is proposed based on the above embodiments, in this embodiment, the prediction module 40 includes:
the calculating module 401 is configured to establish an NCC principle similarity measurement function, and calculate a similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized through the NCC principle similarity measurement function.
A matching prediction module 402, configured to set a similarity threshold, compare the similarity with the similarity threshold, and predict, through the feature recognition model, a to-be-recognized ear sample image corresponding to the to-be-recognized ear LBP texture feature vector when the similarity is greater than the similarity threshold; and when the similarity is smaller than the similarity threshold value, reselecting the similarity for comparison.
It should be understood that the final system will determine the similarity between images using the NCC principle similarity metric function. The extracted feature data of the ear image is searched and matched with the feature template stored in the database, and a threshold value is set, and when the similarity exceeds the threshold value, the result obtained by matching is output. Here is a one-to-many image matching contrast process. Specifically, the classifier is used to classify samples to be detected to obtain classification results corresponding to the classes of the samples to be detected, wherein the samples to be detected are samples of unknown classes, target images are obtained from the classification results of the samples to be detected, and similarity between the images is judged.
It is understood that disease recognition results and solutions can be obtained based on the matching results thereafter. For example, a red and swollen ear lobe indicates discomfort of the throat, such as dry throat, sore throat, etc.; the round bulge of the earlobe, namely the round (bulge central depression) or the papular bulge is arranged on the upper side outside the earlobe, which mostly prompts the patient to have the symptoms of gallbladder discomfort, bitter taste in mouth, vague pain in the biliary region and the like, and can be seen in patients with gallstone, cholecystitis or cholecystectomy; coronary sulcus appears in the ear, namely an oblique groove at the ear lobe, forming an angle of about 45 degrees with the horizontal line, which mostly indicates poor blood supply to the heart, and symptoms such as palpitation and chest distress, which are commonly seen in pulmonary heart disease, coronary heart disease, etc.; the ear lobe is obliquely protruded, and the protrusion is positioned on the ear lobe, can reach the antitragus and forms an angle of about 50 degrees with the horizontal line, so that discomfort of teeth is often prompted, and symptoms such as tooth brushing bleeding and the like can be caused, and the symptoms are common in gingivitis and periodontitis; the obvious brightening of the concha suggests that the heart is not functioning well, and symptoms such as palpitation and chest distress can occur.
The above description is only for illustrative purposes and does not limit the technical solutions of the present application in any way.
As can be seen from the above description, the present embodiment provides a disease prediction system based on ear texture features, including: the characteristic extraction module is used for acquiring an ear texture picture and extracting an ear standard LBP texture characteristic vector from the ear texture picture; the construction module is used for establishing a feature identification model according to the ear standard LBP texture feature vector; the processing module is used for acquiring a to-be-identified ear sampling image, processing the to-be-identified ear sampling image and acquiring an LBP texture feature vector of the to-be-identified ear; and the prediction module is used for setting a similarity threshold, calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, comparing the similarity with the similarity threshold, and predicting the sampled image of the ear to be recognized according to the comparison result. According to the method and the device, the abnormal representation of the ear image acquired by the computer is processed, and then the semantic cognitive characteristic calculation is carried out, so that the functional state of the human body can be accurately and objectively reflected, and the accuracy of classification and identification of the local image sampling characteristic and the disease screening efficiency are improved.
In addition, the embodiment of the invention also provides disease prediction equipment based on the ear texture characteristics. As shown in fig. 6, the ear texture feature-based disease prediction apparatus includes: feature extraction unit 10, construction unit 20, processing unit 30, and prediction unit 40.
A feature extraction unit 10, configured to obtain an ear texture picture, and extract an ear standard LBP texture feature vector from the ear texture picture;
the construction unit 20 is configured to establish a feature identification model according to the ear standard LBP texture feature vector;
the processing unit 30 is configured to obtain a sampling image of an ear to be identified, process the sampling image of the ear to be identified, and obtain an LBP texture feature vector of the ear to be identified;
and the prediction unit 40 is configured to set a similarity threshold, calculate a similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, compare the similarity with the similarity threshold, and predict the sampled image of the ear to be recognized according to a comparison result.
In addition, it should be noted that the above-described embodiments of the apparatus are merely illustrative, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of the modules to implement the purpose of the embodiments according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment can be referred to the ear texture feature-based disease prediction system provided in any embodiment of the present invention, and are not described herein again.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An ear texture feature-based disease prediction system, comprising:
the characteristic extraction module is used for acquiring an ear texture picture and extracting an ear standard LBP texture characteristic vector from the ear texture picture;
the construction module is used for establishing a feature identification model according to the ear standard LBP texture feature vector;
the processing module is used for acquiring a sampling image of an ear to be identified, processing the sampling image of the ear to be identified and acquiring an LBP texture feature vector of the ear to be identified;
and the prediction module is used for setting a similarity threshold, calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, comparing the similarity with the similarity threshold, and predicting the sampled image of the ear to be recognized according to the comparison result.
2. An ear texture based disease prediction system as claimed in claim 1 wherein: the feature extraction module comprises an LBP value acquisition module, a data processing module and a data processing module, wherein the LBP value acquisition module is used for acquiring an ear texture picture, dividing the ear texture picture into small areas of 16X16, acquiring the gray value of each pixel in each small area, comparing the gray value of each pixel with the gray values of 8 pixels adjacent to the pixel, and marking the position of the pixel as 1 when the gray value of each pixel is greater than the gray values of the 8 pixels adjacent to the pixel; when the gray value of each pixel is less than the gray values of 8 pixels adjacent to the pixel, marking the position of the pixel as 0, and counting the position values of all the pixels as the LBP value of the area.
3. An ear texture based disease prediction system as claimed in claim 2 wherein: the feature extraction module comprises an LBP texture feature vector extraction module which is used for setting a spatial arrangement sequence, arranging each small region into a row according to the spatial arrangement sequence, and obtaining an ear standard LBP texture feature vector of the ear texture picture according to an LBP value of each small region.
4. An ear texture based disease prediction system as claimed in claim 3 wherein: the construction module comprises a model construction module used for obtaining corresponding disease information according to the ear standard LBP texture characteristic vector and constructing a characteristic identification model according to the mapping relation between the ear standard LBP texture characteristic vector and the disease information.
5. An ear texture feature based disease prediction system as claimed in claim 4 wherein: the processing module comprises a preprocessing module used for obtaining a sampling image of the ear to be identified, carrying out integrity verification on the sampling image of the ear to be identified, and extracting the LBP texture feature vector of the ear to be identified from the sampling image of the ear to be identified which passes the integrity verification.
6. An ear texture based disease prediction system as claimed in claim 5 wherein: the prediction module comprises a calculation module used for establishing an NCC principle similarity measurement function, and calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized through the NCC principle similarity measurement function.
7. An ear texture based disease prediction system as claimed in claim 6 wherein: the prediction module comprises a matching prediction module for setting a similarity threshold, comparing the similarity with the similarity threshold, and predicting the ear to be recognized sample image corresponding to the LBP texture feature vector of the ear to be recognized through the feature recognition model when the similarity is greater than the similarity threshold; and when the similarity is smaller than the similarity threshold value, reselecting the similarity for comparison.
8. An ear texture feature-based disease prediction apparatus, characterized in that the ear texture feature-based disease prediction apparatus comprises:
the characteristic extraction unit is used for acquiring an ear texture picture and extracting an ear standard LBP texture characteristic vector from the ear texture picture;
the construction unit is used for establishing a feature identification model according to the ear standard LBP texture feature vector;
the processing unit is used for acquiring a sampling image of the ear to be identified, processing the sampling image of the ear to be identified and acquiring an LBP texture feature vector of the ear to be identified;
and the prediction unit is used for setting a similarity threshold, calculating the similarity between the feature recognition model and the LBP texture feature vector of the ear to be recognized, comparing the similarity with the similarity threshold, and predicting the sampled image of the ear to be recognized according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011300974.3A CN112233795A (en) | 2020-11-19 | 2020-11-19 | Disease prediction system based on ear texture features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011300974.3A CN112233795A (en) | 2020-11-19 | 2020-11-19 | Disease prediction system based on ear texture features |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112233795A true CN112233795A (en) | 2021-01-15 |
Family
ID=74123861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011300974.3A Pending CN112233795A (en) | 2020-11-19 | 2020-11-19 | Disease prediction system based on ear texture features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112233795A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658146A (en) * | 2021-08-20 | 2021-11-16 | 合肥合滨智能机器人有限公司 | Nodule grading method and device, electronic equipment and storage medium |
| CN114240936A (en) * | 2022-02-23 | 2022-03-25 | 季华实验室 | Ear analysis and detection device and equipment |
| CN116824168A (en) * | 2023-08-29 | 2023-09-29 | 青岛市中医医院(青岛市海慈医院、青岛市康复医学研究所) | Ear CT feature extraction method based on image processing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040218788A1 (en) * | 2003-01-31 | 2004-11-04 | Geng Z. Jason | Three-dimensional ear biometrics system and method |
| CN106295124A (en) * | 2016-07-27 | 2017-01-04 | 广州麦仑信息科技有限公司 | Utilize the method that multiple image detecting technique comprehensively analyzes gene polyadenylation signal figure likelihood probability amount |
| CN107145741A (en) * | 2017-05-05 | 2017-09-08 | 必应（上海）医疗科技有限公司 | Ear based on graphical analysis examines collecting method and device |
| CN107392223A (en) * | 2017-06-09 | 2017-11-24 | 中国科学院合肥物质科学研究院 | A kind of Adaboost is the same as the NCC complete wheat head recognition methods being combined and system |
| CN109034114A (en) * | 2018-08-22 | 2018-12-18 | 上海掌门科技有限公司 | A kind of ear examines method, equipment, system and computer-readable medium |
| CN109086657A (en) * | 2018-06-08 | 2018-12-25 | 华南理工大学 | A kind of ear detection method, system and model based on machine learning |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN110338763A (en) * | 2019-07-10 | 2019-10-18 | 五邑大学 | A kind of intelligence Chinese medicine examines the image processing method and device of survey |
| US20200037930A1 (en) * | 2018-08-01 | 2020-02-06 | Idx Technologies Inc. | Autonomous diagnosis of ear diseases from biomarker data |
-
2020
- 2020-11-19 CN CN202011300974.3A patent/CN112233795A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040218788A1 (en) * | 2003-01-31 | 2004-11-04 | Geng Z. Jason | Three-dimensional ear biometrics system and method |
| CN106295124A (en) * | 2016-07-27 | 2017-01-04 | 广州麦仑信息科技有限公司 | Utilize the method that multiple image detecting technique comprehensively analyzes gene polyadenylation signal figure likelihood probability amount |
| CN107145741A (en) * | 2017-05-05 | 2017-09-08 | 必应（上海）医疗科技有限公司 | Ear based on graphical analysis examines collecting method and device |
| CN107392223A (en) * | 2017-06-09 | 2017-11-24 | 中国科学院合肥物质科学研究院 | A kind of Adaboost is the same as the NCC complete wheat head recognition methods being combined and system |
| CN109086657A (en) * | 2018-06-08 | 2018-12-25 | 华南理工大学 | A kind of ear detection method, system and model based on machine learning |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| US20200037930A1 (en) * | 2018-08-01 | 2020-02-06 | Idx Technologies Inc. | Autonomous diagnosis of ear diseases from biomarker data |
| CN109034114A (en) * | 2018-08-22 | 2018-12-18 | 上海掌门科技有限公司 | A kind of ear examines method, equipment, system and computer-readable medium |
| CN110338763A (en) * | 2019-07-10 | 2019-10-18 | 五邑大学 | A kind of intelligence Chinese medicine examines the image processing method and device of survey |
Non-Patent Citations (5)
| Title |
|---|
| 侯志涛;孙忠人;刘松涛;尹红娜;孟涛;: "《灵枢经》中耳部望诊方式研究", 湖南中医杂志, no. 05, pages 144 - 145 * |
| 封筠;穆志纯;毛晚堆;: "基于局部二值模式与滤波器融合的人耳识别", 计算机工程与应用, no. 35, pages 196 - 199 * |
| 李春利;沈鲁娟;: "基于改进LBP算子的纹理图像分类方法", 计算机工程与设计, no. 01, pages 240 - 244 * |
| 邵春艳;丁庆海;罗海波;: "基于空间纹理相似性的图像角点特征匹配算法", 计算机应用研究, vol. 33, no. 12, pages 354 - 357 * |
| 闫晓东;王志秦;张建;: "一种基于LBP和DLDA的人耳特征提取方法", 河北理工大学学报(自然科学版), vol. 32, no. 01, pages 45 - 48 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658146A (en) * | 2021-08-20 | 2021-11-16 | 合肥合滨智能机器人有限公司 | Nodule grading method and device, electronic equipment and storage medium |
| CN114240936A (en) * | 2022-02-23 | 2022-03-25 | 季华实验室 | Ear analysis and detection device and equipment |
| CN116824168A (en) * | 2023-08-29 | 2023-09-29 | 青岛市中医医院(青岛市海慈医院、青岛市康复医学研究所) | Ear CT feature extraction method based on image processing |
| CN116824168B (en) * | 2023-08-29 | 2023-11-21 | 青岛市中医医院(青岛市海慈医院、青岛市康复医学研究所) | Ear CT feature extraction method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112233795A (en) | Disease prediction system based on ear texture features | |
| EP3046478B1 (en) | Image analysis techniques for diagnosing diseases | |
| US20190236782A1 (en) | Systems and methods for detecting an indication of malignancy in a sequence of anatomical images | |
| WO2019062835A1 (en) | Ultrasound image processing method and system, and ultrasound diagnosis device | |
| CN111583320B (en) | Breast cancer ultrasonic image typing method and system fusing deep convolutional network and image omics characteristics and storage medium | |
| CN109614869B (en) | Pathological image classification method based on multi-scale compression reward and punishment network | |
| CN110349140B (en) | Traditional Chinese medicine ear diagnosis image processing method and device | |
| WO2018098987A1 (en) | Image processing system and method for tongue diagnosis in traditional chinese medicine | |
| CN110992352A (en) | Automatic infant head circumference CT image measuring method based on convolutional neural network | |
| CN113012173A (en) | Heart segmentation model and pathology classification model training, heart segmentation and pathology classification method and device based on cardiac MRI | |
| Sagar et al. | Color channel based segmentation of skin lesion from clinical images for the detection of melanoma | |
| CN108520283B (en) | Medical image classification method constructed based on brain region indirect relation network | |
| CN111862090A (en) | Method and system for esophageal cancer preoperative management based on artificial intelligence | |
| JP4729188B2 (en) | Gaze detection device | |
| WO2020215485A1 (en) | Fetal growth parameter measurement method, system, and ultrasound device | |
| US20210304410A1 (en) | Methods and Systems Using Video-Based Machine Learning for Beat-To-Beat Assessment of Cardiac Function | |
| Ratheesh et al. | Advanced algorithm for polyp detection using depth segmentation in colon endoscopy | |
| Sciortino et al. | Wavelet analysis and neural network classifiers to detect mid-sagittal sections for nuchal translucency measurement | |
| CN113222996A (en) | Heart segmentation quality evaluation method, device, equipment and storage medium | |
| KR101496198B1 (en) | A three-dimensional ultrasound imaging apparatus and its method of operation | |
| KR20200001911A (en) | Blood pressure monitoring method that can identify the user and blood pressure monitoring system that can identify the user | |
| Lei et al. | Automatic grading of placental maturity based on LIOP and fisher vector | |
| Nirmala et al. | Clinical decision support system for early prediction of Down syndrome fetus using sonogram images | |
| JPH09299366A (en) | Region extract device | |
| CN112507877A (en) | System and method for detecting heart rate under condition of partial video information loss |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |